Fast learning and adaptation in control and machine learning
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/127050 |
| _version_ | 1826195921214373888 |
|---|---|
| author | Gaudio, Joseph Emilio. |
| author2 | Anuradha M. Annaswamy. |
| author_facet | Anuradha M. Annaswamy. Gaudio, Joseph Emilio. |
| author_sort | Gaudio, Joseph Emilio. |
| collection | MIT |
| description | Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020 |
| first_indexed | 2024-09-23T10:17:57Z |
| format | Thesis |
| id | mit-1721.1/127050 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T10:17:57Z |
| publishDate | 2020 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1270502020-09-04T03:34:43Z Fast learning and adaptation in control and machine learning Gaudio, Joseph Emilio. Anuradha M. Annaswamy. Massachusetts Institute of Technology. Department of Mechanical Engineering. Massachusetts Institute of Technology. Department of Mechanical Engineering Mechanical Engineering. Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 249-264). As machine learning methods become more prevalent in society, problems of a dynamical nature will increasingly need to be considered, especially in the interactions of learning-based algorithms with the physical world. The dynamical nature of these problems may include regressors which are time-varying, necessitating new algorithms in machine learning approaches as well as real-time decision making in the presence of uncertainties using adaptive control approaches. Problems of stability, fast learning with analytical guarantees, and constrained nonlinear systems have to be simultaneously addressed. Some of these problems have to be addressed from a machine learning perspective, while others have to be dealt with using adaptive control approaches. Throughout, analytical guarantees must be considered in order to apply machine learning for decision making in real-time, especially for safety-critical systems. This thesis develops fast learning and adaptation algorithms for problems that lie at the intersection of adaptive control and machine learning. From the point of view of adaptive control, this thesis derives algorithms which ensure fast parameter convergence, with minimal overhead in computational complexity. In particular, algorithms with time-varying learning rates are employed to show fast parameter convergence with reduced requirements of persistent excitation, and analysis for time-varying parameters. From the point of view of machine learning, this thesis derives algorithms that are applicable for real-time decision making. In particular, these algorithms ensure fast prediction convergence, which is a necessary feature for satisfactory behavior in real-time systems. Algorithms which take into account natural system constraints, such as input magnitude and rate saturation are also derived order to provide for stability and learning in physically constrained dynamical systems. Throughout the thesis, analytical guarantees for all algorithms are provided. by Joseph Emilio Gaudio. Ph. D. Ph.D. Massachusetts Institute of Technology, Department of Mechanical Engineering 2020-09-03T17:44:12Z 2020-09-03T17:44:12Z 2020 2020 Thesis https://hdl.handle.net/1721.1/127050 1191716147 eng MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 264 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Mechanical Engineering. Gaudio, Joseph Emilio. Fast learning and adaptation in control and machine learning |
| title | Fast learning and adaptation in control and machine learning |
| title_full | Fast learning and adaptation in control and machine learning |
| title_fullStr | Fast learning and adaptation in control and machine learning |
| title_full_unstemmed | Fast learning and adaptation in control and machine learning |
| title_short | Fast learning and adaptation in control and machine learning |
| title_sort | fast learning and adaptation in control and machine learning |
| topic | Mechanical Engineering. |
| url | https://hdl.handle.net/1721.1/127050 |
| work_keys_str_mv | AT gaudiojosephemilio fastlearningandadaptationincontrolandmachinelearning |